Borrowing it
Nothing to install: this file belongs to MadaraUchiha-314/the-loop. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/MadaraUchiha-314/the-loop/main/CLAUDE.mdgit clone --depth 1 https://github.com/MadaraUchiha-314/the-loopWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/madarauchiha-314/the-loop/claude-md)<a href="https://agentmods.dev/instructions/madarauchiha-314/the-loop/claude-md"><img src="https://agentmods.dev/badge/instructions/madarauchiha-314/the-loop/claude-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00691 | $0.00691 |
| Opus 5 | $0.00345 | $0.00345 |
| Sonnet 5 | $0.00138 | $0.00138 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
the-loop CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — working in the-loop's own repository
This repository is the-loop, and it dogfoods its own PDLC. the-loop is a
product-development-lifecycle harness (shipped as a Claude Code / Cursor plugin). When you
work in this repo you are both building the harness and expected to use it: build
the-loop through the-loop.
Why this file exists
the-loop's operating rules normally reach an agent through the plugin's SessionStart
hook (hooks/hooks.json) or, in Cursor, the always-applied rule (rules/the-loop.mdc).
Those only fire when the-loop is installed as a plugin in a consuming project — they do
not fire in the-loop's own sessions, because a fresh Claude Code cloud / web
checkout doesn't self-install the plugin. This CLAUDE.md is the in-repo equivalent: it is
auto-loaded in every session here and carries the same reminder, so cloud/web sessions run
the loop instead of shipping plain one-off PRs. (This is the gap
issue #73 surfaced — the phase
labels sit unused precisely because past work bypassed the loop.)
What to do
- Read the operating model first.
.the-loop/harness-config.yaml(this project's config) and the bundled skillskills/the-loop/SKILL.mdare the source of truth for how work is done here;skills/the-loop/reference/workflow.mdhas the phase-by-phase detail. Follow them — don't re-derive the process. - Every change is a work item with a ticket. Nothing is worked without a GitHub issue.
Create and lock the spec chain (
requirements → design → testing-plan → tasks) underdocs/specs/<id>/before writing code, scaling rigor to the change perconfig.autonomytiers: a trivial (tier 1–2) change is autonomous-complete and needs no full spec; a tier 3+ change does. When unsure which, follow the skill. - Keep the phase label in sync. Apply and advance the
loop:<phase>label on the ticket at every transition (loop:not-started → … → loop:complete), mirrored indocs/specs/<id>/execution-log.md. Using the loop is what keeps these labels populated (seedocs/reports/labels-and-dashboards.md). - Follow the skill's remaining rules, don't restate them here: self/critic-review
before escalating, a paper trail for every human decision, and updating the affected
capability docs (
docs/capabilities/) in the same PR as the change. Seeskills/the-loop/SKILL.mdand itsreference/.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 42 lines · 691 tokens per session scan A 31c227114708
the-loop CLAUDE.md is an instructions file published in the GitHub repository MadaraUchiha-314/the-loop (4 stars, last pushed 3d ago), licensed MIT. It adds 691 tokens to every session, about $0.0035 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.